Skip to content
DraconiticResearch
Search Sources API
203,234 studies31 sourcesUpdated 52 min ago
Peer-reviewedCC BY-NCDrug design, development and therapy

Explainable Machine Learning for Predicting Early Response to Perampanel in Pediatric Epilepsy: A Real-World Study.

  • Xin Rao1,2
  • Ping Wu3,4
  • Xi Lin5
  • Jie-Min Zhang1,2
  • Xiao-Jun Lin6
  • Zhou-Jie Liu1,2
  • Rong-Fang Lin1,2
  • Yue-Wen Chen1,2
6 affiliations
  1. 1Department of Pharmacy, The First Affiliated Hospital, Fujian Medical University, Fuzhou, Fujian, People's Republic of China.
  2. 2Department of Pharmacy, National Regional Medical Center, Binhai Campus of the First Affiliated Hospital, Fujian Medical University, Fuzhou, Fujian, People's Republic of China.
  3. 3Department of Pathology, The First Affiliated Hospital, Fujian Medical University, Fuzhou, Fujian, People's Republic of China.
  4. 4Department of Pathology, National Regional Medical Center, Binhai Campus of the First Affiliated Hospital, Fujian Medical University, Fuzhou, Fujian, People's Republic of China.
  5. 5Department of Pediatrics, The First Affiliated Hospital, Fujian Medical University, Fuzhou, Fujian, People's Republic of China.
  6. 6School of Medicine, Zhangzhou College of Science and Technology, Zhangzhou, Fujian, People's Republic of China.
Read full textPDFDOICite

Abstract

Objective

To develop and validate an early prediction model for perampanel (PER) response in children with epilepsy (CWE) using clinical covariates and ensemble learning, to support individualized treatment decisions.Methods

A retrospective cohort of 325 CWE (< 15 years) treated with PER from January 2021 to December 2025 was enrolled. Treatment response at 2 months was defined as the study outcome (responder vs non-responder). Key covariates were screened using Light Gradient Boosting Machine (LGBM) feature importance ranking combined with forward feature selection. Five core algorithms were selected from 11 candidate algorithms, and a soft voting ensemble model was constructed, interpreted using SHapley Additive exPlanations (SHAP), and subjected to age-stratified analysis.Results

Seven covariates were ultimately included. The ensemble model achieved a test set AUC of 0.861 (95% CI: 0.727-0.963), accuracy of 0.892 (95% CI: 0.815-0.954), and specificity of 0.940 (95% CI: 0.860-1.000); the mean 5-fold cross-validation AUC was 0.915 ± 0.064; external validation yielded an AUC of 0.798 (95% CI: 0.668-0.900). Decision curve analysis (DCA) demonstrated improved net benefit within threshold probabilities of 0.07 to 0.75. Calibration curves showed good calibration (brier score = 0.12). SHAP analysis identified the number of antiseizure medications (ASMs, 43.7%), PER maintenance dose (17.0%), and CYP3A4 enzyme inducers (CYP3A4-I, 13.1%) as the primary predictors, all positively associated with treatment non-response. Exploratory age-stratified SHAP analysis (≤72 months vs >72 months) suggested that the associations of polytherapy, higher PER maintenance dose, and shorter disease duration with predicted treatment non-response may be more pronounced in younger children.Conclusion

In this pediatric cohort, the ensemble model demonstrated good discrimination and calibration for predicting early perampanel response at 2 months. The number of ASMs, PER maintenance dose, and CYP3A4-I were the leading predictors of treatment non-response.

Related

  1. Predicting atropine treatment response heterogeneity in pediatric myopia using explainable machine learning: an on-treatment longitudinal monitoring framework
    Jun-Wei Chen, Chieh-Han Yu, Tzu-Chi Liu +2
    Scientific ReportsPeer-reviewedCC BYFull textEpidemiology & public healthDOAJ
  2. Explainable machine learning and deep learning models for predicting in-hospital mortality in burn patients
    Reza Zarei, Maral Taghizadeh Shalmaei, Masiha Mobayen +2
    Scientific ReportsPeer-reviewedCC BY-NC-ND 4.0Full textEpidemiology & public healthCrossref
  3. Predicting subsequent-year physical fitness assessment failure in university students using longitudinal data and explainable machine learning
    Lan Luo, Fawei Huang, Baixia Li
    BMC Public HealthPeer-reviewedCC BY-NC-ND 4.0PhysiologyCrossref
  4. Ultrasound-based deep learning radiomics with explainable machine learning for predicting benign and malignant thyroid nodules in lymphocytic thyroiditis: a multicenter study
    Ji Zhou, Wenwu Lu, Wei Wei +6
    Quantitative imaging in medicine and surgeryPeer-reviewedCC BY-NC-NDFull textMedical imaging & radiologyEurope PMC
  5. Stage-Aware and Explainable Machine Learning for Predicting IVF Implantation
    H. Sharma, K. Yemelong, A. Carmona +2
    medRxivPreprintCC BY-NC-NDFull textObstetrics, gynaecology & paediatricsmedRxiv

Cite

BibTeXRIS
BibTeX
@article{rao2026explainable,
  title = {{Explainable Machine Learning for Predicting Early Response to Perampanel in Pediatric Epilepsy: A Real-World Study.}},
  author = {Xin Rao and Ping Wu and Xi Lin and Jie-Min Zhang and Xiao-Jun Lin and Zhou-Jie Liu and Rong-Fang Lin and Yue-Wen Chen},
  journal = {Drug design, development and therapy},
  year = {2026},
  month = oct,
  doi = {10.2147/dddt.s648788},
  url = {https://europepmc.org/article/MED/42968942},
  note = {CC BY-NC},
}
RIS
TY  - JOUR
TI  - Explainable Machine Learning for Predicting Early Response to Perampanel in Pediatric Epilepsy: A Real-World Study.
AU  - Xin Rao
AU  - Ping Wu
AU  - Xi Lin
AU  - Jie-Min Zhang
AU  - Xiao-Jun Lin
AU  - Zhou-Jie Liu
AU  - Rong-Fang Lin
AU  - Yue-Wen Chen
PY  - 2026
DA  - 2026/10/28
JO  - Drug design, development and therapy
DO  - 10.2147/dddt.s648788
UR  - https://europepmc.org/article/MED/42968942
AB  - Objective  To develop and validate an early prediction model for perampanel (PER) response in children with epilepsy (CWE) using clinical covariates and ensemble learning, to support individualized treatment decisions.Methods  A retrospective cohort of 325 CWE (< 15 years) treated with PER from January 2021 to December 2025 was enrolled. Treatment response at 2 months was defined as the study outcome (responder vs non-responder). Key covariates were screened using Light Gradient Boosting Machine (LGBM) feature importance ranking combined with forward feature selection. Five core algorithms were selected from 11 candidate algorithms, and a soft voting ensemble model was constructed, interpreted using SHapley Additive exPlanations (SHAP), and subjected to age-stratified analysis.Results  Seven covariates were ultimately included. The ensemble model achieved a test set AUC of 0.861 (95% CI: 0.727-0.963), accuracy of 0.892 (95% CI: 0.815-0.954), and specificity of 0.940 (95% CI: 0.860-1.000); the mean 5-fold cross-validation AUC was 0.915 ± 0.064; external validation yielded an AUC of 0.798 (95% CI: 0.668-0.900). Decision curve analysis (DCA) demonstrated improved net benefit within threshold probabilities of 0.07 to 0.75. Calibration curves showed good calibration (brier score = 0.12). SHAP analysis identified the number of antiseizure medications (ASMs, 43.7%), PER maintenance dose (17.0%), and CYP3A4 enzyme inducers (CYP3A4-I, 13.1%) as the primary predictors, all positively associated with treatment non-response. Exploratory age-stratified SHAP analysis (≤72 months vs >72 months) suggested that the associations of polytherapy, higher PER maintenance dose, and shorter disease duration with predicted treatment non-response may be more pronounced in younger children.Conclusion  In this pediatric cohort, the ensemble model demonstrated good discrimination and calibration for predicting early perampanel response at 2 months. The number of ASMs, PER maintenance dose, and CYP3A4-I were the leading predictors of treatment non-response.
SN  - 1177-8881
ER  -